The state of the art of sensor placement methods in structural health monitoring

2006 ◽  
Author(s):  
Dong-Sheng Li ◽  
Hong-Nan Li
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
State Of The Art ◽  
Sensor Placement ◽  
The State ◽  
Structural Health

scholarly journals The State of the Art of Data Science and Engineering in Structural Health Monitoring

Engineering ◽  
2019 ◽  
Vol 5 (2) ◽  
pp. 234-242 ◽  
Author(s):  
Yuequan Bao ◽  
Zhicheng Chen ◽  
Shiyin Wei ◽  
Yang Xu ◽  
Zhiyi Tang ◽  
...  
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Data Science ◽  
State Of The Art ◽  
The State ◽  
Science And Engineering ◽  
Structural Health

scholarly journals Deep residual network framework for structural health monitoring

2020 ◽  
pp. 147592172091837 ◽  
Author(s):  
Ruhua Wang ◽  
Chencho ◽  
Senjian An ◽  
Jun Li ◽  
Ling Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Structural Health Monitoring ◽  
Convolutional Neural Network ◽  
Health Monitoring ◽  
Damage Identification ◽  
State Of The Art ◽  
Experimental Studies ◽  
The State ◽  
Residual Network ◽  
Structural Health

Convolutional neural networks have been widely employed for structural health monitoring and damage identification. The convolutional neural network is currently considered as the state-of-the-art method for structural damage identification due to its capabilities of efficient and robust feature learning in a hierarchical manner. It is a tendency to develop a convolutional neural network with a deeper architecture to gain a better performance. However, when the depth of the network increases to a certain level, the performance will degrade due to the gradient vanishing issue. Residual neural networks can avoid the problem of vanishing gradients by utilizing skip connections, which allows the information flowing to the next layer through identity mappings. In this article, a deep residual network framework is proposed for structural health monitoring of civil engineering structures. This framework is composed of purely residual blocks which operate as feature extractors and a fully connected layer as a regressor. It learns the damage-related features from the vibration characteristics such as mode shapes and maps them into the damage index labels, for example, stiffness reductions of structures. To evaluate the efficacy and robustness of the proposed framework, an intensive evaluation is conducted with both numerical and experimental studies. The comparison between the proposed approach and the state-of-the-art models, including a sparse autoencoder neural network, a shallow convolutional neural network and a convolutional neural network with the same structure but without skip connections, is conducted. In the numerical studies, a 7-storey steel frame is investigated. Four scenarios with considering measurement noise and finite element modelling errors in the data sets are studied. The proposed framework consistently outperforms the state-of-the-art models in all the scenarios, especially for the most challenging scenario, which includes both measurement noise and uncertainties. Experimental studies on a prestressed concrete bridge in the laboratory are conducted. The proposed framework demonstrates consistent damage prediction results on this beam with the state-of-the-art models.

Optimization of sensor placement for structural health monitoring: a review

2019 ◽  
Vol 18 (3) ◽  
pp. 963-988 ◽  
Author(s):  
Wieslaw Ostachowicz ◽  
Rohan Soman ◽  
Pawel Malinowski
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
State Of The Art ◽  
Optimization Algorithms ◽  
Sensor Placement ◽  
Problem Definition ◽  
Structural Health ◽  
Definition Of ◽  
Major Argument ◽  
The Cost

The deployment cost of the structural health monitoring (SHM) system is the major argument against the more widespread use of the structural health monitoring techniques. Optimization of sensor placement offers an opportunity to reduce the cost of the SHM system without compromising on the quality of the monitoring approach. Several studies in the area of optimization of sensor placement for SHM applications have been undertaken but the approach has been rather application specific. This article is an attempt to present an unbiased state of the art of the work carried out in the area. The article is targeted towards researchers working in the field of structural health monitoring and optimization of sensor placement as well as practising engineers. This article reviews the work in the area of optimization of sensor placement. It first presents the definition of the optimization problem and then describes each step of the optimization. The current state of the art is then classified based on the techniques for which the optimization of sensor placement has been optimized. The article covers vibration-based monitoring, strain monitoring and elastic wave-based monitoring, as in the eyes of the authors these three techniques are most commonly used and accepted in the SHM community. The article later discusses the different optimization algorithms that have been applied in the literature. The article highlights the different pitfalls of the optimization algorithms and the countermeasures different researchers have proposed to overcome the known shortcomings. In the later section, the multi-objective optimization or the problem definition, keeping in mind the structural as well as executional demands, is discussed. A section has also been developed to showcase the use of optimization of sensor placement techniques’ data fusion–based systems.

scholarly journals Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2778 ◽  
Author(s):  
Mohsen Azimi ◽  
Armin Eslamlou ◽  
Gokhan Pekcan
Keyword(s):  
Deep Learning ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
High Speed ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Data Driven ◽  
Structural Health ◽  
Promising Tool ◽  
Significant Attention

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

Validation of Impedance-Based Structural Health Monitoring in a Simulated Biomedical Implant System

2018 ◽  
Author(s):  
Robert I. Ponder ◽  
Mohsen Safaei ◽  
Steven R. Anton
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Orthopedic Implants ◽  
The United States ◽  
The State ◽  
Piezoelectric Transducers ◽  
Bone Implant ◽  
Electromechanical Impedance ◽  
Structural Health ◽  
Number Of Patients

Total Knee Replacement (TKR) is an important and in-demand procedure for the aging population of the United States. In recent decades, the number of TKR procedures performed has shown an increase. This pattern is expected to continue in the coming decades. Despite medical advances in orthopedic surgery, a high number of patients, approximately 20%, are dissatisfied with their procedure outcomes. Common causes that are suggested for this dissatisfaction include loosening of the implant components as well as infection. To eliminate loosening as a cause, it is necessary to determine the state of the implant both intra- and post-operatively. Previous research has focused on passively sensing the compartmental loads between the femoral and tibial components. Common methods include using strain gauges or even piezoelectric transducers to measure force. An alternative to this is to perform real-time structural health monitoring (SHM) of the implant to determine changes in the state of the system. A commonly investigated method of SHM, referred to as the electromechanical impedance (EMI) method, involves using the coupled electromechanical properties of piezoelectric transducers to measure the host structure’s condition. The EMI method has already shown promise in aerospace and infrastructure applications, but has seen limited testing for use in the biomechanical field. This work is intended to validate the EMI method for use in detecting damage in cemented bone-implant interfaces, with TKR being used as a case study to specify certain experimental parameters. An experimental setup which represents the various material layers found in a bone-implant interface is created with various damage conditions to determine the ability for a piezoelectric sensor to detect and quantify the change in material state. The objective of this work is to provide validation as well as a foundation on which additional work in SHM of orthopedic implants and structures can be performed.

scholarly journals A Multiobjective Perspective to Optimal Sensor Placement by Using a Decomposition-Based Evolutionary Algorithm in Structural Health Monitoring

2020 ◽  
Vol 10 (21) ◽  
pp. 7710
Author(s):  
Tsung-Yueh Lin ◽  
Jin Tao ◽  
Hsin-Haou Huang
Keyword(s):  
Structural Health Monitoring ◽  
Evolutionary Algorithm ◽  
Health Monitoring ◽  
Sensor Placement ◽  
Frame Structure ◽  
Mode Shapes ◽  
Beam Model ◽  
Optimal Sensor Placement ◽  
Modal Assurance Criterion ◽  
Structural Health

The objective of optimal sensor placement in a dynamic system is to obtain a sensor layout that provides as much information as possible for structural health monitoring (SHM). Whereas most studies use only one modal assurance criterion for SHM, this work considers two additional metrics, signal redundancy and noise ratio, combining into three optimization objectives: Linear independence of mode shapes, dynamic information redundancy, and vibration response signal strength. A modified multiobjective evolutionary algorithm was combined with particle swarm optimization to explore the optimal solution sets. In the final determination, a multiobjective decision-making (MODM) strategy based on distance measurement was used to optimize the aforementioned objectives. We applied it to a reduced finite-element beam model of a reference building and compared it with other selection methods. The results indicated that MODM suitably balanced the objective functions and outperformed the compared methods. We further constructed a three-story frame structure for experimentally validating the effectiveness of the proposed algorithm. The results indicated that complete structural modal information can be effectively obtained by applying the MODM approach to identify sensor locations.

Sign in / Sign up

Export Citation Format

Share Document